© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57204
    Prev
    Next
    INDEX
    Explanations

    intense adjectives that describe qualities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.08
    ernity
    -0.06
    cond
    -0.06
    ниÑı
    -0.06
    aways
    -0.06
    ertz
    -0.06
     UsersController
    -0.06
     behalf
    -0.06
    .
    -0.06
     ref
    -0.05
    POSITIVE LOGITS
     же
    0.11
    åŃIJãģ¯
    0.10
    ForMember
    0.09
    nature
    0.09
    人ãģ¯
    0.08
     totiž
    0.08
    oret
    0.08
    ÙĢÙĢÙĢÙĢÙĢÙĢÙĢÙĢ
    0.08
    eker
    0.08
    EMS
    0.08
    Activations Density 0.223%

    No Known Activations